Christopher N. Rowley
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Christopher N. Rowley has a total of 195 co-authors. Here are the top co-authors by number of shared publications:
Tom K. Woo
The University of Western Ontario, Department of Chemistry, London, Ontario, N6A 5B7 Canada, Department of Chemistry, Memorial University of Newfoundland, St. John’s, NL, A1B 3X7, Canada, and Centre for Catalysis Research and Innovation, Department of Chemistry, University of Ottawa, Ottawa, Ontario K1N 6N5, Canada
14 shared publications- Erin R. Johnson
Dalhousie University
11 shared publications - Ernest Awoonor-Williams
Novartis Institutes for BioMedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States
11 shared publications - Nguyen Thien Phuc Tu
Carleton University
8 shared publications Ernest Awoonor-Williams
7 shared publications- Haibo Yu
University of Wollongong
6 shared publications
Latest Publications
- 6 August 2026
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 165 (5)
Δ-learning for transferable machine learning interatomic potentials
Machine-learning interatomic potentials (MLIPs) trained by directly learning the total interatomic interaction energies can suffer from limited transferability, unphysical behavior beyond a finite cutoff, and large errors for out-of-distribution geometries such as transition states and uncommon conformers. We evaluate Δ-learning (delta-learning) as a remedy by training an ANI-style high-dimensional neural network (HDNNP) potential as a correction to predict PBE0/aug-cc-pVTZ energies from a third-order tight-binding density functional theory (DFTB3) baseline model. On a held-out test set derived from the modified ANI-1x training set, the Δ-learning model (named ANIDFTB-Δ) achieves a mean absolute error (MAE) of 0.82 kcal/mol, while the HDNNP model (ANIPBE0-Direct) has an MAE of 2.01 kcal/mol. On selected GMTKN55 benchmarks, the Δ model systematically improves relative energies for conformers and tautomers and avoids catastrophic outliers on challenging structures. The good physical description of DFTB3 significantly reduces the error in proton-transfer transition states in the PX13 benchmark and intermolecular interactions in the DES370K dataset in comparison with reference target PBE0. The long-range electrostatics in DFTB3 also partially correct the long-range behavior of local descriptor MLIPs outside of their predetermined cutoff, reducing the MAE from 0.098 to 0.019 kcal/mol. The computational cost of this method is incrementally more expensive than DFTB3 alone, making it practical for extensive simulations of moderately sized systems, although the DFTB3 step makes the Δ model much more costly than a simple HDNNP alone.
- 6 August 2026
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 165 (5)
Δ-learning for transferable machine learning interatomic potentials
Machine-learning interatomic potentials (MLIPs) trained by directly learning the total interatomic interaction energies can suffer from limited transferability, unphysical behavior beyond a finite cutoff, and large errors for out-of-distribution geometries such as transition states and uncommon conformers. We evaluate Δ-learning (delta-learning) as a remedy by training an ANI-style high-dimensional neural network (HDNNP) potential as a correction to predict PBE0/aug-cc-pVTZ energies from a third-order tight-binding density functional theory (DFTB3) baseline model. On a held-out test set derived from the modified ANI-1x training set, the Δ-learning model (named ANIDFTB-Δ) achieves a mean absolute error (MAE) of 0.82 kcal/mol, while the HDNNP model (ANIPBE0-Direct) has an MAE of 2.01 kcal/mol. On selected GMTKN55 benchmarks, the Δ model systematically improves relative energies for conformers and tautomers and avoids catastrophic outliers on challenging structures. The good physical description of DFTB3 significantly reduces the error in proton-transfer transition states in the PX13 benchmark and intermolecular interactions in the DES370K dataset in comparison with reference target PBE0. The long-range electrostatics in DFTB3 also partially correct the long-range behavior of local descriptor MLIPs outside of their predetermined cutoff, reducing the MAE from 0.098 to 0.019 kcal/mol. The computational cost of this method is incrementally more expensive than DFTB3 alone, making it practical for extensive simulations of moderately sized systems, although the DFTB3 step makes the Δ model much more costly than a simple HDNNP alone.
- 21 November 2025
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 129 (48) , 12518-12528
Long-Range Interactions in High-Dimensional Neural Network Potentials: A Benchmark Study for Small Organic Molecules
Many machine learning potentials (MLPs) rely on representations of the total energy in terms of the positions of the atoms in their local environment, using either a cutoff radius or a limited number of message-passing layers. This restricts their ability to model long-range intermolecular interactions accurately. This limitation can be addressed by explicitly incorporating long-range electrostatic and dispersion interactions into the MLP framework. In this paper, we investigate the impact of augmenting high-dimensional neural network potentials (HDNNPs) with both electrostatic and dispersion corrections on the prediction of gas-phase intermolecular interactions between small organic molecules. We employ a machine learning-based charge equilibration (QEq) scheme to model electrostatics and the Machine-Learning eXchange-hole Dipole-Moment (MLXDM) model to account for dispersion. The resulting model, CombineNet, integrates these long-range terms with short-range atomic energies trained on density functional theory (DFT) data and achieves a low mean absolute error (MAE) of 0.59 kcal/mol (root-mean-square error (RMSE) of 3.38 meV/atom) against CCSD(T)/CBS benchmarks on the DES370K test set. Notably, electrostatic interactions derived from Hirshfeld charges tend to underestimate long-range effects, whereas the minimal basis iterative stockholder (MBIS) charges yield more accurate interaction trends. For reliable modeling of molecular dimers, the training set must capture both the dissociation limit and the transition region near the cutoff radius.
- 21 November 2025
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 129 (48) , 12518-12528
Long-Range Interactions in High-Dimensional Neural Network Potentials: A Benchmark Study for Small Organic Molecules
Many machine learning potentials (MLPs) rely on representations of the total energy in terms of the positions of the atoms in their local environment, using either a cutoff radius or a limited number of message-passing layers. This restricts their ability to model long-range intermolecular interactions accurately. This limitation can be addressed by explicitly incorporating long-range electrostatic and dispersion interactions into the MLP framework. In this paper, we investigate the impact of augmenting high-dimensional neural network potentials (HDNNPs) with both electrostatic and dispersion corrections on the prediction of gas-phase intermolecular interactions between small organic molecules. We employ a machine learning-based charge equilibration (QEq) scheme to model electrostatics and the Machine-Learning eXchange-hole Dipole-Moment (MLXDM) model to account for dispersion. The resulting model, CombineNet, integrates these long-range terms with short-range atomic energies trained on density functional theory (DFT) data and achieves a low mean absolute error (MAE) of 0.59 kcal/mol (root-mean-square error (RMSE) of 3.38 meV/atom) against CCSD(T)/CBS benchmarks on the DES370K test set. Notably, electrostatic interactions derived from Hirshfeld charges tend to underestimate long-range effects, whereas the minimal basis iterative stockholder (MBIS) charges yield more accurate interaction trends. For reliable modeling of molecular dimers, the training set must capture both the dissociation limit and the transition region near the cutoff radius.
- Open Access
- 10 August 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Long-Range Interactions in High-Dimensional Neural Network Potentials: A Benchmark Study for Small Organic Molecules
Many machine learning potentials (MLPs) rely on representations of the total energy in terms of the positions of the atoms in their local environment, using either a cutoff radius or a limited number of message-passing layers. This restricts their ability to model long-range intermolecular interactions accurately. This limitation can be addressed by explicitly incorporating long-range electrostatic and dispersion interactions into the MLP framework. In this paper, we investigate the impact of augmenting high-dimensional neural network potentials (HDNNPs) with both electrostatic and dispersion corrections on the prediction of gas-phase intermolecular interactions between small organic molecules. We employ a machine learning-based charge equilibration (QEq) scheme to model electrostatics and the Machine-Learning eXchange-hole Dipole Moment (MLXDM) model to account for dispersion. The resulting model, CombineNet, integrates these long-range terms with short-range atomic energies trained on density functional theory (DFT) data and achieves a low mean absolute error (MAE) of 0.59~kcal/mol (root mean square error (RMSE) of 3.38~meV/atom) against CCSD(T)/CBS benchmarks on the DES370K test set. Notably, electrostatic interactions derived from Hirshfeld charges tend to underestimate long-range effects, whereas the Minimal Basis Iterative Stockholder (MBIS) charges yield more accurate interaction trends. For reliable modeling of molecular dimers, the training set must capture both the dissociation limit and the transition region near the cutoff radius. For reliable modeling of molecular dimers, the training set must cover the full range of interest of intermolecular distances.
- 10 August 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessLong-Range Interactions in High-Dimensional Neural Network Potentials: A Benchmark Study for Small Organic Molecules
Many machine learning potentials (MLPs) rely on representations of the total energy in terms of the positions of the atoms in their local environment, using either a cutoff radius or a limited number of message-passing layers. This restricts their ability to model long-range intermolecular interactions accurately. This limitation can be addressed by explicitly incorporating long-range electrostatic and dispersion interactions into the MLP framework. In this paper, we investigate the impact of augmenting high-dimensional neural network potentials (HDNNPs) with both electrostatic and dispersion corrections on the prediction of gas-phase intermolecular interactions between small organic molecules. We employ a machine learning-based charge equilibration (QEq) scheme to model electrostatics and the Machine-Learning eXchange-hole Dipole Moment (MLXDM) model to account for dispersion. The resulting model, CombineNet, integrates these long-range terms with short-range atomic energies trained on density functional theory (DFT) data and achieves a low mean absolute error (MAE) of 0.59~kcal/mol (root mean square error (RMSE) of 3.38~meV/atom) against CCSD(T)/CBS benchmarks on the DES370K test set. Notably, electrostatic interactions derived from Hirshfeld charges tend to underestimate long-range effects, whereas the Minimal Basis Iterative Stockholder (MBIS) charges yield more accurate interaction trends. For reliable modeling of molecular dimers, the training set must capture both the dissociation limit and the transition region near the cutoff radius. For reliable modeling of molecular dimers, the training set must cover the full range of interest of intermolecular distances.
- 24 January 2025
- Published by Elsevier in Biophysical Journal
- Vol. 124 (4) , 587-589
Channel rectification made simple
- 24 January 2025
- Published by Elsevier in Biophysical Journal
- Vol. 124 (4) , 587-589
Channel rectification made simple
- Top Cited PapersOpen Access
- 20 September 2024
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 128 (41) , 9976-10042
CHARMM at 45: Enhancements in Accessibility, Functionality, and Speed
Since its inception nearly a half century ago, CHARMM has been playing a central role in computational biochemistry and biophysics. Commensurate with the developments in experimental research and advances in computer hardware, the range of methods and applicability of CHARMM have also grown. This review summarizes major developments that occurred after 2009 when the last review of CHARMM was published. They include the following: new faster simulation engines, accessible user interfaces for convenient workflows, and a vast array of simulation and analysis methods that encompass quantum mechanical, atomistic, and coarse-grained levels, as well as extensive coverage of force fields. In addition to providing the current snapshot of the CHARMM development, this review may serve as a starting point for exploring relevant theories and computational methods for tackling contemporary and emerging problems in biomolecular systems. CHARMM is freely available for academic and nonprofit research at https://academiccharmm.org/program.
- 20 September 2024
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 128 (41) , 9976-10042
Top Cited PapersOpen AccessCHARMM at 45: Enhancements in Accessibility, Functionality, and Speed
Since its inception nearly a half century ago, CHARMM has been playing a central role in computational biochemistry and biophysics. Commensurate with the developments in experimental research and advances in computer hardware, the range of methods and applicability of CHARMM have also grown. This review summarizes major developments that occurred after 2009 when the last review of CHARMM was published. They include the following: new faster simulation engines, accessible user interfaces for convenient workflows, and a vast array of simulation and analysis methods that encompass quantum mechanical, atomistic, and coarse-grained levels, as well as extensive coverage of force fields. In addition to providing the current snapshot of the CHARMM development, this review may serve as a starting point for exploring relevant theories and computational methods for tackling contemporary and emerging problems in biomolecular systems. CHARMM is freely available for academic and nonprofit research at https://academiccharmm.org/program.
- 21 August 2024
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 128 (35) , 8290-8302
Modeling Intermolecular Interactions with Exchange-Hole Dipole Moment Dispersion Corrections to Neural Network Potentials
Neural network potentials (NNPs) are an innovative approach for calculating the potential energy and forces of a chemical system. In principle, these methods are capable of modeling large systems with an accuracy approaching that of a high-level ab initio calculation, but with a much smaller computational cost. Due to their training to density-functional theory (DFT) data and neglect of long-range interactions, some classes of NNPs require an additional term to include London dispersion physics. In this Perspective, we discuss the requirements for a dispersion model for use with an NNP, focusing on the MLXDM (Machine Learned eXchange-Hole Dipole Moment) model developed by our groups. This model is based on the DFT-based XDM dispersion correction, which calculates interatomic dispersion coefficients in terms of atomic moments and polarizabilities, both of which can be approximated effectively using neural networks.
- 21 August 2024
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 128 (35) , 8290-8302
Modeling Intermolecular Interactions with Exchange-Hole Dipole Moment Dispersion Corrections to Neural Network Potentials
Neural network potentials (NNPs) are an innovative approach for calculating the potential energy and forces of a chemical system. In principle, these methods are capable of modeling large systems with an accuracy approaching that of a high-level ab initio calculation, but with a much smaller computational cost. Due to their training to density-functional theory (DFT) data and neglect of long-range interactions, some classes of NNPs require an additional term to include London dispersion physics. In this Perspective, we discuss the requirements for a dispersion model for use with an NNP, focusing on the MLXDM (Machine Learned eXchange-Hole Dipole Moment) model developed by our groups. This model is based on the DFT-based XDM dispersion correction, which calculates interatomic dispersion coefficients in terms of atomic moments and polarizabilities, both of which can be approximated effectively using neural networks.
- Open Access
- 25 July 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (9) , 1776-1792
Graph neural networks for identifying protein-reactive compounds
GNN recognizes protein reactivity of covalent inhibitor futibatinib with 99.2% confidence score.
- 25 July 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (9) , 1776-1792
Open AccessGraph neural networks for identifying protein-reactive compounds
GNN recognizes protein reactivity of covalent inhibitor futibatinib with 99.2% confidence score.
- Open Access
- 6 June 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Graph Neural Networks for Identifying Protein-Reactive Compounds
The identification of protein-reactive electrophilic compounds is critical to the design of new covalent modifier drugs, screening for toxic compounds, and the exclusion of reactive compounds from high throughput screening. In this work, we employ traditional and graph machine learning (ML) algorithms to classify molecules being reactive towards proteins or nonreactive. For training data, we built a new dataset, ProteinReactiveDB, composed primarily of covalent and noncovalent inhibitors from the DrugBank, BindingDB, and CovalentInDB databases. To assess the transferability of the trained models, we created a custom set of covalent and noncovalent inhibitors, which was constructed from the recent literature. Baseline models were developed using Morgan fingerprints as training inputs, but they performed poorly when applied to compounds outside the training set. We then trained various Graph Neural Networks (GNNs), with the best GNN model achieving an Area Under the Receiver Operator Characteristic (AUROC) curve of 0.80, precision of 0.89, and recall of 0.72. We also explore the interpretability of these GNNs using Gradient Activation Mapping (GradCAM), which shows regions of the molecules GNNs deem most relevant when making a prediction. These maps indicated that our trained models can identify electrophilic functional groups in a molecule and classify molecules as protein-reactive based on their presence. We demonstrate the use of these models by comparing their performance against common chemical filters, identifying covalent modifiers in the ChEMBL database and generating a putative covalent inhibitor based on an established noncovalent inhibitor.
- 6 June 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessGraph Neural Networks for Identifying Protein-Reactive Compounds
The identification of protein-reactive electrophilic compounds is critical to the design of new covalent modifier drugs, screening for toxic compounds, and the exclusion of reactive compounds from high throughput screening. In this work, we employ traditional and graph machine learning (ML) algorithms to classify molecules being reactive towards proteins or nonreactive. For training data, we built a new dataset, ProteinReactiveDB, composed primarily of covalent and noncovalent inhibitors from the DrugBank, BindingDB, and CovalentInDB databases. To assess the transferability of the trained models, we created a custom set of covalent and noncovalent inhibitors, which was constructed from the recent literature. Baseline models were developed using Morgan fingerprints as training inputs, but they performed poorly when applied to compounds outside the training set. We then trained various Graph Neural Networks (GNNs), with the best GNN model achieving an Area Under the Receiver Operator Characteristic (AUROC) curve of 0.80, precision of 0.89, and recall of 0.72. We also explore the interpretability of these GNNs using Gradient Activation Mapping (GradCAM), which shows regions of the molecules GNNs deem most relevant when making a prediction. These maps indicated that our trained models can identify electrophilic functional groups in a molecule and classify molecules as protein-reactive based on their presence. We demonstrate the use of these models by comparing their performance against common chemical filters, identifying covalent modifiers in the ChEMBL database and generating a putative covalent inhibitor based on an established noncovalent inhibitor.
- Open Access
- 7 May 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Modeling Intermolecular Interactions With XDM Dispersion Corrections to Neural Network Potentials
Neural network potentials (NNPs) are an innovative approach for calculating the potential energy and forces of a chemical system. In principle, these methods are capable of modeling large systems with an accuracy approaching that of a high-level ab initio calculation but with a much smaller computational cost. Due to their training to density-functional theory (DFT) data and neglect of long-range interactions, some classes of NNPs require an additional term to include London dispersion physics. In this perspective, we discuss the requirements for a dispersion model for use with an NNP, focusing on the MLXDM (Machine Learned eXchange Hole Dipole Moment) model developed by our groups. This model is based on the DFT-based XDM dispersion correction, which calculates interatomic dispersion coefficients in terms of atomic moments and polarizabilities, both of which can be effectively approximated using neural networks.
- 7 May 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessModeling Intermolecular Interactions With XDM Dispersion Corrections to Neural Network Potentials
Neural network potentials (NNPs) are an innovative approach for calculating the potential energy and forces of a chemical system. In principle, these methods are capable of modeling large systems with an accuracy approaching that of a high-level ab initio calculation but with a much smaller computational cost. Due to their training to density-functional theory (DFT) data and neglect of long-range interactions, some classes of NNPs require an additional term to include London dispersion physics. In this perspective, we discuss the requirements for a dispersion model for use with an NNP, focusing on the MLXDM (Machine Learned eXchange Hole Dipole Moment) model developed by our groups. This model is based on the DFT-based XDM dispersion correction, which calculates interatomic dispersion coefficients in terms of atomic moments and polarizabilities, both of which can be effectively approximated using neural networks.
- 15 February 2024
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 146 (8) , 5650-5660
Controlling Reactivity and Selectivity in the Mizoroki–Heck Reaction: High Throughput Evaluation of 1,5-Diaza-3,7-diphosphacyclooctane Ligands
We report a high throughput evaluation of the Mizoroki-Heck reaction of diverse olefin coupling partners. Comparison of different ligands revealed the 1,5-diaza-3,7-diphosphacyclooctane (P2N2) scaffold to be more broadly applicable than common "gold standard" ligands, demonstrating that this family of readily accessible diphosphines has unrecognized potential in organic synthesis. In particular, two structurally related P2N2 ligands were identified to enable the regiodivergent arylation of styrenes. By simply altering the phosphorus substituent from a phenyl to tert-butyl group, both the linear and branched Mizoroki-Heck products can be obtained in high regioisomeric ratios. Experimental and computational mechanistic studies were performed to further probe the origin of selectivity, which suggests that both ligands coordinate to the metal in a similar manner but that rigid positioning of the phosphorus substituent forces contact with the incoming olefin in a π-π interaction (for P-Ph ligands) or with steric clash (for P-tBu ligands), dictating the regiocontrol.
- 15 February 2024
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 146 (8) , 5650-5660
Controlling Reactivity and Selectivity in the Mizoroki–Heck Reaction: High Throughput Evaluation of 1,5-Diaza-3,7-diphosphacyclooctane Ligands
We report a high throughput evaluation of the Mizoroki-Heck reaction of diverse olefin coupling partners. Comparison of different ligands revealed the 1,5-diaza-3,7-diphosphacyclooctane (P2N2) scaffold to be more broadly applicable than common "gold standard" ligands, demonstrating that this family of readily accessible diphosphines has unrecognized potential in organic synthesis. In particular, two structurally related P2N2 ligands were identified to enable the regiodivergent arylation of styrenes. By simply altering the phosphorus substituent from a phenyl to tert-butyl group, both the linear and branched Mizoroki-Heck products can be obtained in high regioisomeric ratios. Experimental and computational mechanistic studies were performed to further probe the origin of selectivity, which suggests that both ligands coordinate to the metal in a similar manner but that rigid positioning of the phosphorus substituent forces contact with the incoming olefin in a π-π interaction (for P-Ph ligands) or with steric clash (for P-tBu ligands), dictating the regiocontrol.